基于多层图多角度的道路交叉口车辆跟踪

doi:10.3778/j.issn.1002-8331.2101-0195

摘要/Abstract

摘要： 针对交叉路口下不确定运动流车辆跟踪问题，提出一种基于多层图多角度对车辆进行跟踪的方法。构建多层图形将各运动流分配到具有不同邻域的不同层；将多角度视图下所有多层图形映射到所选定主视图中；通过求解映射主视图下运动流最短路径，实现对车辆轨迹的跟踪。由跟踪实验及分析，结果表明，该方法对交叉路口不确定运动流的车辆运行轨迹可有效预测并进行跟踪，且跟踪效果与地面真实情况基本一致，误判率维持6%以下，具有实际应用价值，可为智能交通中车辆的跟踪提供新的方法。

关键词: 车辆跟踪, 多层图, 视频流, 多角度, 最短路径

Abstract: Aiming at the problem of tracking uncertain vehicle motion flow at intersections, a method based on multi-level graphs and multi-angle is proposed. Firstly, each motion flow is assigned to different layers with diverse neighborhoods by using the constructed multi-layer graphs; secondly, all multi-layer graphics under multi-angle views are mapped to the selected main view; finally, the vehicle tracking is realized by solving the shortest path of the mapping main view motion flow. Through the experiment and analysis of vehicle tracking at intersections, the results show that this method can effectively predict vehicle trajectory for uncertain vehicle flow at intersections, and the misjudgment rate between tracking effect and the real situation on the ground is less than 6%, which can provide a new method for vehicle tracking in intelligent transportation.

Key words: vehicle tracking, multi-layer graphs, video stream, multi-angle, shortest path

刘向前, 闫娟, 杨慧斌, 贾茜伟. 基于多层图多角度的道路交叉口车辆跟踪[J]. 计算机工程与应用, 2022, 58(17): 263-269.

LIU Xiangqian, YAN Juan, YANG Huibin, JIA Xiwei. Road Intersections Vehicle Tracking Based on Multi-Layer Graphs and Multi-Angle[J]. Computer Engineering and Applications, 2022, 58(17): 263-269.

参考文献

[1] CHANG X，LIU Y，SHEN M.Resilient control design for lateral motion regulation of intelligent vehicle[J].IEEE/ASME Transactions on Mechatronics，2019，24（6）：2488-2497.
[2] ZHAO X，WANG X，MA L，et al.Fuzzy approximation based asymptotic tracking control for a class of uncertain switched nonlinear systems[J].IEEE Transactions on Fuzzy Systems，2020，28（4）：632-644.
[3] SIVARAMAN S，TRIVEDI M M.Looking at vehicles on the road：a survey of vision-based vehicle detection，tracking，and behavior analysis[J].IEEE Transactions on Intelligent Transportation Systems，2013，14（4）：1773-1795.
[4] YANG Y，BILODEAU G.Multiple-object tracking with kernelized correlation filters in urban mixed traffic[C]//2017 14th Conf on Computer and Robot Vision（CRV），Edmonton，AB，Canada，2017：209-216.
[5] DATONDJI S R E，DUPUIS Y，SUBIRATS P，et al.A survey of vision-based traffic monitoring of road intersections[J].IEEE Transactions on Intelligent Transportation Systems，2016，17（10）：2681-2698.
[6] SHIRAZI M S，MORRIS B T.Looking at intersections：a survey of intersection monitoring，behavior and safety analysis of recent studies[J].IEEE Transactions on Intelligent Transportation Systems，2017，18（1）：4-24.
[7] VEERARAGHAVAN H，MASOUD O，PAPANIKOLOPOULOS N P.Computer vision algorithm for intersection monitoring monitoring[J].IEEE Transactions on Intelligent Transportation Systems，2003，4（2）：78-79.
[8] LIRA G，KOKKINOGENIS Z，ROSSETTI R J F，et al.A computer-vision approach to traffic analysis over intersections[C]//IEEE 19th Int Conf on Intelligent Transportation Systems（ITSC），Rio de Janeiro，Brazil，2016：47-53.
[9] SONG X，NEVATIA R.Detection and tracking of moving vehicles in crowded scenes[C]//IEEE Workshop on Motion and Video Computing，2007.
[10] WU C，YANG W，TING H，et al.Traffic pattern modeling，trajectory classification and vehicle tracking within urban intersections[C]//2017 Int Smart Cities Conf，Wuxi，China，2017：1-5.
[11] OOI H L，BILODEAU G A，SAUNIER N，et al.Multiple-object tracking in urban traffic scenes with a multiclass object detector[C]//Advances in Visual Computing，2018：727-736.
[12] PROMMOOL P，AUEPHANWIRIYAKUL S，THEERA-UMPON N.Vision-based automatic vehicle counting system using motion estimation with Taylor series approximation[C]//IEEE International Conference on Control System，Computing and Engineering，2016：485-489.
[13] DEL ROSARIO J R B，BANDALA A A，DADIOS E P.Multi-view multi-object tracking in an intelligent transportation system：a literature review[C]//2017 IEEE 9th Int Conf on Humanoid，Nanotechnology，Information Technology Communication and Control，Environment and Management，Manila，Philippines，2017：1-4.
[14] ATEV S，PAPANIKOLOPOULOS N.Multi-view 3D vehicle tracking with aconstrained filter[C]//2008 IEEE Int Conf on Robotics and AutomationPasadena，CA，USA，2008：2277-2282.
[15] SUBEDI S，TANG H.Development of a multiple-camera 3d vehicle tracking system for traffic data collection at intersections[J].IET Intelligent Transport Systems，2019，13（4）：614-621.
[16] WU M，ZHANG G，BI N，et al.Multiview vehicle tracking by graph-matching model[C]//The 12th IEEE Conf on Computer Vision and Pattern Recognition（CVPR） Workshops，Long Beach，California，USA，2019：94-101.
[17] 马泊宁.基于视频流的车辆跟踪算法研究[D].成都：电子科技大学，2020.
MA Poning.Research on vehicle tracking algorithm based on video stream[D].Chendu：University of Electronic Science and Technology，2020.
[18] 陈鑫.基于视频流的车辆跟踪算法的研究与应用[D].北京：北京工业大学，2019.
CHEN Xin.Research and application of vehicle tracking algorithm based on video stream[D].Beijing：Beijing University of Technology，2019.
[19] JATI G，GUNAWAN A A S，JATMIKO W.Dynamic swarm particle for fast motion vehicle tracking[J].IEEE Transactions on Intelligent Transportation Systems，2020，42（1）：54-66.
[20] 杜亚鹏.图像拼接的关键技术研究[D].成都：电子科技大学，2020.
DU Yapeng.Research on key technology of image mosaic[D].Chendu：University of Electronic Science and Technology，2020.